FR3050846B1 - DEVICE AND METHOD FOR DISTRIBUTING CONVOLUTION DATA OF A CONVOLUTIONAL NEURON NETWORK - Google Patents
DEVICE AND METHOD FOR DISTRIBUTING CONVOLUTION DATA OF A CONVOLUTIONAL NEURON NETWORK Download PDFInfo
- Publication number
- FR3050846B1 FR3050846B1 FR1653744A FR1653744A FR3050846B1 FR 3050846 B1 FR3050846 B1 FR 3050846B1 FR 1653744 A FR1653744 A FR 1653744A FR 1653744 A FR1653744 A FR 1653744A FR 3050846 B1 FR3050846 B1 FR 3050846B1
- Authority
- FR
- France
- Prior art keywords
- convolution
- distributing
- permutation
- input
- neuron network
- Prior art date
- Legal status (The legal status is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the status listed.)
- Active
Links
Classifications
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06N—COMPUTING ARRANGEMENTS BASED ON SPECIFIC COMPUTATIONAL MODELS
- G06N3/00—Computing arrangements based on biological models
- G06N3/02—Neural networks
- G06N3/08—Learning methods
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06N—COMPUTING ARRANGEMENTS BASED ON SPECIFIC COMPUTATIONAL MODELS
- G06N3/00—Computing arrangements based on biological models
- G06N3/02—Neural networks
- G06N3/04—Architecture, e.g. interconnection topology
- G06N3/049—Temporal neural networks, e.g. delay elements, oscillating neurons or pulsed inputs
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06N—COMPUTING ARRANGEMENTS BASED ON SPECIFIC COMPUTATIONAL MODELS
- G06N3/00—Computing arrangements based on biological models
- G06N3/02—Neural networks
- G06N3/04—Architecture, e.g. interconnection topology
- G06N3/045—Combinations of networks
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06N—COMPUTING ARRANGEMENTS BASED ON SPECIFIC COMPUTATIONAL MODELS
- G06N3/00—Computing arrangements based on biological models
- G06N3/02—Neural networks
- G06N3/06—Physical realisation, i.e. hardware implementation of neural networks, neurons or parts of neurons
- G06N3/063—Physical realisation, i.e. hardware implementation of neural networks, neurons or parts of neurons using electronic means
Landscapes
- Engineering & Computer Science (AREA)
- Physics & Mathematics (AREA)
- Theoretical Computer Science (AREA)
- Health & Medical Sciences (AREA)
- Life Sciences & Earth Sciences (AREA)
- Biomedical Technology (AREA)
- Biophysics (AREA)
- General Health & Medical Sciences (AREA)
- Data Mining & Analysis (AREA)
- Evolutionary Computation (AREA)
- Computational Linguistics (AREA)
- Molecular Biology (AREA)
- Computing Systems (AREA)
- General Engineering & Computer Science (AREA)
- General Physics & Mathematics (AREA)
- Mathematical Physics (AREA)
- Software Systems (AREA)
- Artificial Intelligence (AREA)
- Neurology (AREA)
- Complex Calculations (AREA)
Abstract
L'invention propose un dispositif pour distribuer des coefficients de convolution d'au moins un noyau de convolution d'un réseau de neurones convolutionnel portés par un bus d'entrée (201) vers un ensemble d'unités de traitement dans un calculateur basé sur une architecture de réseau de neurones convolutionnel. Le dispositif comprend au moins un réseau de permutation (30) pilotée par au moins une unité de contrôle (32), le réseau de permutation comprenant un ensemble de permutateurs (30) agencés pour effectuer des décalages circulaires d'au moins une partie du bus d'entrée. Pour chaque noyau de convolution, chaque unité de contrôle est configurée pour piloter dynamiquement certains au moins des permutateurs des réseaux de permutation (30) en réponse à un événement d'entrée appliqué sur le noyau de convolution et d'au moins un paramètre représentant la taille maximale des noyaux de convolution.The invention provides a device for distributing convolution coefficients of at least one convolution core of a convolutional neural network carried by an input bus (201) to a set of processing units in a calculator based on a convolutional neural network architecture. The device comprises at least one permutation network (30) driven by at least one control unit (32), the permutation network comprising a set of permutators (30) arranged to perform circular offsets of at least a portion of the bus input. For each convolution kernel, each control unit is configured to dynamically drive at least some permutators of the permutation networks (30) in response to an input event applied to the convolution kernel and at least one parameter representing the maximum size of the convolution nuclei.
Priority Applications (4)
Application Number | Priority Date | Filing Date | Title |
---|---|---|---|
FR1653744A FR3050846B1 (en) | 2016-04-27 | 2016-04-27 | DEVICE AND METHOD FOR DISTRIBUTING CONVOLUTION DATA OF A CONVOLUTIONAL NEURON NETWORK |
PCT/EP2017/060017 WO2017186830A1 (en) | 2016-04-27 | 2017-04-27 | Device and method for distributing convolutional data of a convolutional neural network |
EP17720462.5A EP3449424A1 (en) | 2016-04-27 | 2017-04-27 | Device and method for distributing convolutional data of a convolutional neural network |
US16/095,923 US11423296B2 (en) | 2016-04-27 | 2017-04-27 | Device and method for distributing convolutional data of a convolutional neural network |
Applications Claiming Priority (2)
Application Number | Priority Date | Filing Date | Title |
---|---|---|---|
FR1653744 | 2016-04-27 | ||
FR1653744A FR3050846B1 (en) | 2016-04-27 | 2016-04-27 | DEVICE AND METHOD FOR DISTRIBUTING CONVOLUTION DATA OF A CONVOLUTIONAL NEURON NETWORK |
Publications (2)
Publication Number | Publication Date |
---|---|
FR3050846A1 FR3050846A1 (en) | 2017-11-03 |
FR3050846B1 true FR3050846B1 (en) | 2019-05-03 |
Family
ID=57113426
Family Applications (1)
Application Number | Title | Priority Date | Filing Date |
---|---|---|---|
FR1653744A Active FR3050846B1 (en) | 2016-04-27 | 2016-04-27 | DEVICE AND METHOD FOR DISTRIBUTING CONVOLUTION DATA OF A CONVOLUTIONAL NEURON NETWORK |
Country Status (4)
Country | Link |
---|---|
US (1) | US11423296B2 (en) |
EP (1) | EP3449424A1 (en) |
FR (1) | FR3050846B1 (en) |
WO (1) | WO2017186830A1 (en) |
Families Citing this family (21)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
US10360470B2 (en) * | 2016-10-10 | 2019-07-23 | Gyrfalcon Technology Inc. | Implementation of MobileNet in a CNN based digital integrated circuit |
US10366328B2 (en) * | 2017-09-19 | 2019-07-30 | Gyrfalcon Technology Inc. | Approximating fully-connected layers with multiple arrays of 3x3 convolutional filter kernels in a CNN based integrated circuit |
US11164071B2 (en) * | 2017-04-18 | 2021-11-02 | Samsung Electronics Co., Ltd. | Method and apparatus for reducing computational complexity of convolutional neural networks |
JP2019200675A (en) * | 2018-05-17 | 2019-11-21 | 東芝メモリ株式会社 | Processing device and data processing method |
US20190392287A1 (en) | 2018-06-22 | 2019-12-26 | Samsung Electronics Co., Ltd. | Neural processor |
FR3085517B1 (en) | 2018-08-31 | 2020-11-13 | Commissariat Energie Atomique | CALCULATOR ARCHITECTURE OF A CONVOLUTION LAYER IN A CONVOLUTIONAL NEURON NETWORK |
EP3857447A4 (en) * | 2018-09-30 | 2022-06-29 | BOE Technology Group Co., Ltd. | Apparatus and method for image processing, and system for training neural network |
CN109493300B (en) * | 2018-11-15 | 2022-05-20 | 湖南鲲鹏智汇无人机技术有限公司 | Aerial image real-time defogging method based on FPGA (field programmable Gate array) convolutional neural network and unmanned aerial vehicle |
US11526753B2 (en) * | 2019-02-12 | 2022-12-13 | Irida Labs S.A. | System and a method to achieve time-aware approximated inference |
US11211944B2 (en) | 2019-04-17 | 2021-12-28 | Samsung Electronics Co., Ltd. | Mixed-precision compression with random access |
US11671111B2 (en) | 2019-04-17 | 2023-06-06 | Samsung Electronics Co., Ltd. | Hardware channel-parallel data compression/decompression |
US11880760B2 (en) | 2019-05-01 | 2024-01-23 | Samsung Electronics Co., Ltd. | Mixed-precision NPU tile with depth-wise convolution |
CN112215329B (en) * | 2019-07-09 | 2023-09-29 | 杭州海康威视数字技术股份有限公司 | Convolutional calculation method and device based on neural network |
CN112308107A (en) | 2019-07-25 | 2021-02-02 | 智力芯片有限责任公司 | Event-based feature classification in reconfigurable and time-coded convolutional spiking neural networks |
CN110728303B (en) * | 2019-09-12 | 2022-03-11 | 东南大学 | Dynamic self-adaptive computing array based on convolutional neural network data complexity |
US11625453B1 (en) | 2019-12-12 | 2023-04-11 | Amazon Technologies, Inc. | Using shared data bus to support systolic array tiling |
KR20210105053A (en) * | 2020-02-18 | 2021-08-26 | 에스케이하이닉스 주식회사 | Calculation circuit and deep learning system including the same |
CN111783997B (en) * | 2020-06-29 | 2024-04-23 | 杭州海康威视数字技术股份有限公司 | Data processing method, device and equipment |
CN112101284A (en) * | 2020-09-25 | 2020-12-18 | 北京百度网讯科技有限公司 | Image recognition method, training method, device and system of image recognition model |
CN113570031B (en) * | 2021-06-08 | 2024-02-02 | 中国科学院深圳先进技术研究院 | Convolution operation processing method, electronic device and computer readable storage medium |
KR20240092304A (en) * | 2022-12-14 | 2024-06-24 | 리벨리온 주식회사 | Neural processor |
Family Cites Families (4)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
US7237055B1 (en) * | 2003-10-22 | 2007-06-26 | Stretch, Inc. | System, apparatus and method for data path routing configurable to perform dynamic bit permutations |
US9342780B2 (en) * | 2010-07-30 | 2016-05-17 | Hewlett Packard Enterprise Development Lp | Systems and methods for modeling binary synapses |
FR3015068B1 (en) * | 2013-12-18 | 2016-01-01 | Commissariat Energie Atomique | SIGNAL PROCESSING MODULE, IN PARTICULAR FOR NEURONAL NETWORK AND NEURONAL CIRCUIT |
FR3025344B1 (en) * | 2014-08-28 | 2017-11-24 | Commissariat Energie Atomique | NETWORK OF CONVOLUTIONAL NEURONS |
-
2016
- 2016-04-27 FR FR1653744A patent/FR3050846B1/en active Active
-
2017
- 2017-04-27 EP EP17720462.5A patent/EP3449424A1/en active Pending
- 2017-04-27 US US16/095,923 patent/US11423296B2/en active Active
- 2017-04-27 WO PCT/EP2017/060017 patent/WO2017186830A1/en active Application Filing
Also Published As
Publication number | Publication date |
---|---|
US11423296B2 (en) | 2022-08-23 |
US20190156201A1 (en) | 2019-05-23 |
FR3050846A1 (en) | 2017-11-03 |
EP3449424A1 (en) | 2019-03-06 |
WO2017186830A1 (en) | 2017-11-02 |
Similar Documents
Publication | Publication Date | Title |
---|---|---|
FR3050846B1 (en) | DEVICE AND METHOD FOR DISTRIBUTING CONVOLUTION DATA OF A CONVOLUTIONAL NEURON NETWORK | |
JP2020525688A5 (en) | ||
Narita | Match or mismatch? Learning and inertia in school choice | |
JP2019096006A5 (en) | ||
WO2017064554A8 (en) | Method for arranging workloads in a software defined automation system | |
US8848019B1 (en) | System and method for enabling virtual live video | |
FR3050855B1 (en) | DEVICE AND METHOD FOR CONVOLUTION CALCULATION OF A CONVOLUTIONAL NEURON NETWORK | |
US20190251443A1 (en) | Automatically scaling neural networks based on load | |
CN108369504A (en) | It is distributed to the update by model-driven of variation topology | |
US20200005171A1 (en) | System, method and computer product for classifying user expertise | |
CN108170538A (en) | A kind of information processing method, device and electronic equipment | |
FR3069682B1 (en) | CALCULATOR FOR PULSE NEURON NETWORK WITH MAXIMUM AGGREGATION | |
FR3055715B1 (en) | METHODS AND DEVICES FOR CONTOURING INTERNAL CACHE OF ADVANCED DRAM MEMORY CONTROLLER | |
EP3229160A3 (en) | Method for configuring a medical instrument, system for con-figuring a medical instrument, computer program product and computer readable medium | |
US20180157554A1 (en) | Resolving conflicts between multiple software and hardware processes | |
CN108108893A (en) | the seat management method of conference system | |
JP2021056658A (en) | Information processing system, information processing method and information processing program | |
US20180318622A1 (en) | Cognitive solution to enhance firefighting capabilities | |
DE15736113T1 (en) | Mobile cast receiver for computer and entertainment devices | |
EP3832416A3 (en) | Data models for defining data transmission workflow and facilitating data communication | |
WO2023039114A1 (en) | Artificial intelligence based technologies for improving patient intake | |
Lengler et al. | Note on the coefficient of variations of neuronal spike trains | |
MA49416B1 (en) | Systems and methods for controlling production and / or distribution lines | |
WO2019118271A9 (en) | Parallel multivalue reductions | |
JP2019046465A5 (en) | Providing device, providing method, and providing program |
Legal Events
Date | Code | Title | Description |
---|---|---|---|
PLFP | Fee payment |
Year of fee payment: 2 |
|
PLSC | Publication of the preliminary search report |
Effective date: 20171103 |
|
PLFP | Fee payment |
Year of fee payment: 3 |
|
PLFP | Fee payment |
Year of fee payment: 4 |
|
PLFP | Fee payment |
Year of fee payment: 5 |
|
PLFP | Fee payment |
Year of fee payment: 6 |
|
PLFP | Fee payment |
Year of fee payment: 7 |
|
PLFP | Fee payment |
Year of fee payment: 8 |